© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 2024
    Prev
    Next
    INDEX
    Explanations

    information about making or baking pies, probably in a recipe context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    464
    +0.10
    0.5%
    99
    +0.10
    0.5%
    659
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.01
    76
    +0.10
    0.01
    99
    +0.10
    0.01
    Negative Logits
    iveness
    -0.80
     Examiner
    -0.76
    ulk
    -0.73
    runners
    -0.71
    angers
    -0.68
    nen
    -0.67
    sers
    -0.66
    strong
    -0.64
    iqueness
    -0.63
    afety
    -0.63
    POSITIVE LOGITS
     pie
    1.09
    pie
    1.08
    ced
    1.07
     pies
    1.03
    cing
    1.03
     crust
    0.98
    Pie
    0.97
     Pie
    0.92
    zo
    0.91
    ces
    0.85
    Activations Density 0.017%

    No Known Activations